Microsoft researchers have created an artificial intelligence-based system that learned how to get the maximum score on the addictive 1980s video game Ms. Pac-Man, using a divide-and-conquer method that could have broad implications for teaching AI agents to do complex tasks that augment human capabilities. The team from Maluuba, a Canadian deep learning startup acquired by Microsoft earlier this year, used a branch of AI called reinforcement learning to play the Atari 2600 version of Ms. Pac-Man perfectly. Using that method, the team achieved the maximum score possible of 999,990. Doina Precup, an associate professor of computer science at McGill University in Montreal said that's a significant achievement among AI researchers, who have been using various videogames to test their systems but have found Ms. Pac-Man among the most difficult to crack. But Precup said she was impressed not just with what the researchers achieved but with how they achieved it.
If you thought solving a Rubik's cube was difficult, you were right and maths can back you up. A recent study shows that the question of whether a scrambled Rubik's cube of any size can be solved in a given number of moves is what's called NP-complete – that's maths lingo for a problem even mathematicians find hard to solve. To prove that the problem is NP-complete, Massachusetts Institute of Technology researchers Erik Demaine, Sarah Eisenstat, and Mikhail Rudoy showed that figuring out how to solve a Rubik's cube with any number of squares on a side in the smallest number of moves will also give you a solution to another problem known to be NP-complete: the Hamiltonian path problem. That question asks whether there is route that visits each vertex exactly once in a given graph consisting of a collection of vertices connected by edges, like a triangle, pentagram, or the vast connections in a social network such as Facebook. It's reminiscent of the travelling salesperson problem, which aims to find the shortest route that visits several cities only once, probably the most famous NP-complete question of all.
A deep-learning algorithm has been developed which can solve the Rubik's cube faster than any human can. It never fails to complete the puzzle, with a 100 per cent success rate and managing it in around 20 moves. Humans can beat the AI's mark of 18 seconds, the world record is around four seconds, but it is far more inefficient and people often require around 50 moves. It was created by University of California Irvine and can be tried out here. Given an unsolved cube, the machine must decide whether a specific move is an improvement on the existing configuration.
Researchers have developed an AI algorithm which can solve a Rubik's cube in a fraction of a second, according to a study published in the journal Nature Machine Intelligence. The system, known as DeepCubeA, uses a form of machine learning which teaches itself how to play in order to crack the puzzle without being specifically coached by humans. "Artificial intelligence can defeat the world's best human chess and Go players, but some of the more difficult puzzles, such as the Rubik's Cube, had not been solved by computers, so we thought they were open for AI approaches," Pierre Baldi, one of the developers of the algorithm and computer scientist from the University of California, Irvine, said in a statement. According to Baldi, the latest development could herald a new generation of artificial intelligence (AI) deep-learning systems which are more advanced than those used in commercially available applications such as Siri and Alexa. "These systems are not really intelligent; they're brittle, and you can easily break or fool them," Baldi said.
Humans can manipulate Rubik's cubes with relative ease, but robots have historically had a tougher go of it. That's not to suggest there aren't exceptions to the rule -- an MIT invention recently solved a cube in a record-breaking 0.38 seconds -- but they typically involve purpose-built motors and controls. Encouragingly, a group of researchers at Tencent and the Chinese University of Hong Kong say they've designed a Rubik's cube manipulator that uses multi-fingered hands. "Dexterous in-hand manipulation is a key building block for robots to achieve human-level dexterity, and accomplish everyday tasks which involve rich contact," wrote the researchers. "Despite concerted progress, reliable multi-fingered dexterous hand manipulation has remained an open challenge, due to its complex contact patterns, high dimensional action space, and fragile mechanical structure."